parser.add_argument("frame_path")
parser.add_argument("output_file")
parser.add_argument("--overlap", type=float, default=0.7)
parser.add_argument("--max_level", type=int, default=8)
parser.add_argument("--time_step", type=float, default=1)
parser.add_argument("--version", default="1.2")
parser.add_argument("--avoid", default=None, type=str)
parser.add_argument("--dataset",
default="activitynet",
choices=["thumos14", "activitynet"])
args = parser.parse_args()
name_pattern = "img_*.jpg" if args.modality == "rgb" else "flow_x_*.jpg"
if args.dataset == "activitynet":
db = ANetDB.get_db(args.version)
db.try_load_file_path(args.frame_path)
elif args.dataset == "thumos14":
db = THUMOSDB.get_db()
db.try_load_file_path(args.frame_path)
if args.subset == "testing":
args.subset = "test"
else:
raise ValueError("Unknown dataset {}".format(args.dataset))
avoid_list = [x.strip() for x in open(args.avoid)] if args.avoid else []
videos = db.get_subset_videos(args.subset)
ctx = multiprocessing.get_context('spawn')
net = BinaryClassifier(num_class,
args.num_body_segments,
args,
dropout=args.dropout,
test_mode=True)
checkpoint = torch.load(args.weights)
print("model epoch {} loss: {}".format(checkpoint['epoch'],
checkpoint['best_loss']))
base_dict = {
'.'.join(k.split('.')[1:]): v
for k, v in list(checkpoint['state_dict'].items())
}
db = ANetDB.get_db("1.3")
val_videos = db.get_subset_videos(args.subset)
loader = torch.utils.data.DataLoader(BinaryDataSet(
args.feat_root,
args.feat_model,
test_prop_file,
subset_videos=val_videos,
exclude_empty=True,
body_seg=args.num_body_segments,
input_dim=args.input_dim,
test_mode=True,
use_flow=args.use_flow,
test_interval=args.frame_interval,
verbose=False,
num_local=args.num_local),
parser.add_argument("--cls_scores", type=str, default=None,
help='classification scores, if set to None, will use groundtruth labels')
parser.add_argument("--subset", type=str, default='validation', choices=['training', 'validation', 'testing'])
parser.add_argument("--iou_thresh", type=float, nargs='+', default=[0.5, 0.75, 0.95])
parser.add_argument("--score_weights", type=float, nargs='+', default=None, help='')
parser.add_argument("--write_proposals", type=str, default=None, help='')
parser.add_argument("--minimum_len", type=float, default=0, help='minimum length of a proposal, in second')
parser.add_argument("--reg_score_files", type=str, nargs='+', default=None)
parser.add_argument("--frame_path", type=str, default='/mnt/SSD/ActivityNet/anet_v1.2_extracted_340/')
parser.add_argument('--frame_interval', type=int, default=16)
args = parser.parse_args()
if args.dataset == 'activitynet':
db = ANetDB.get_db(args.anet_version)
db.try_load_file_path('/mnt/SSD/ActivityNet/anet_v1.2_extracted_340/')
elif args.dataset == 'thumos14':
db = THUMOSDB.get_db()
db.try_load_file_path('/mnt/SSD/THUMOS14/')
# rename subset test
if args.subset == 'testing':
args.subset = 'test'
else:
raise ValueError("unknown dataset {}".format(args.dataset))
def compute_frame_count(video_info, frame_path, name_pattern):
# first count frame numbers
try:
video_name = video_info.id
def main():
global args, best_loss
args = parser.parse_args()
dataset_configs = get_actionness_configs(args.dataset)
sampling_configs = dataset_configs['sampling']
num_class = dataset_configs['num_class']
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
db = ANetDB.get_db("1.3")
# set the directory for the rgb features
if args.feat_model == 'i3d_rgb' or args.feat_model == 'i3d_rgb_trained':
args.input_dim = 1024
elif args.feat_model == 'inception_resnet_v2' or args.feat_model == 'inception_resnet_v2_trained':
args.input_dim = 1536
if args.use_flow:
if not args.only_flow:
args.input_dim += 1024
else:
args.input_dim = 1024
print(("=> the input features are extracted from '{}' and the dim is '{}'"
).format(args.feat_model, args.input_dim))
# if reduce the dimension of input feature first
if args.reduce_dim > 0:
assert args.reduce_dim % args.n_head == 0, "reduce_dim {} % n_head {} != 0".format(
args.reduce_dim, args.n_head)
args.d_k = int(args.reduce_dim // args.n_head)
args.d_v = args.d_k
else:
assert args.input_dim % args.n_head == 0, "input_dim {} % n_head {} != 0".format(
args.input_dim, args.n_head)
args.d_k = int(args.input_dim // args.n_head)
args.d_v = args.d_k
args.d_model = args.n_head * args.d_k
if not os.path.exists(args.result_path):
os.makedirs(args.result_path)
if args.pos_enc:
save_path = os.path.join(
args.result_path, '_'.join(
(args.att_kernel_type, 'N' + str(args.n_layers))))
else:
save_path = os.path.join(
args.result_path, '_'.join(
(args.att_kernel_type, 'N' + str(args.n_layers)))) + '_nopos'
if args.num_local > 0:
save_path = save_path + '_loc' + str(args.num_local) + args.local_type
if args.dilated_mask:
save_path += '_dilated'
if args.groupwise_heads > 0:
save_path = save_path + '_G' + str(args.groupwise_heads)
if len(args.roi_poolsize) > 0:
save_path = save_path + '_roi' + str(args.roi_poolsize)
model_name = os.path.split(save_path)[1]
# logger = Logger('./logs/{}'.format(model_name))
logger = None
model = BinaryClassifier(num_class,
args.num_body_segments,
args,
dropout=args.dropout)
model = torch.nn.DataParallel(model, device_ids=None).cuda()
cudnn.enabled = False
# cudnn.benchmark = True
pin_memory = True
train_prop_file = 'data/{}_proposal_list.txt'.format(
dataset_configs['train_list'])
val_prop_file = 'data/{}_proposal_list.txt'.format(
dataset_configs['test_list'])
train_videos = db.get_subset_videos('training')
val_videos = db.get_subset_videos('validation')
train_loader = torch.utils.data.DataLoader(BinaryDataSet(
args.feat_root,
args.feat_model,
train_prop_file,
train_videos,
exclude_empty=True,
body_seg=args.num_body_segments,
input_dim=args.d_model,
prop_per_video=args.prop_per_video,
fg_ratio=6,
bg_ratio=6,
num_local=args.num_local,
use_flow=args.use_flow,
only_flow=args.only_flow),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=True)
# val_loader = torch.utils.data.DataLoader(
# BinaryDataSet(args.feat_root, args.feat_model, val_prop_file, val_videos,
# exclude_empty=True, body_seg=args.num_body_segments,
# input_dim=args.d_model, prop_per_video=args.prop_per_video,
# fg_ratio=6, bg_ratio=6, num_local=args.num_local,
# use_flow=args.use_flow, only_flow=args.only_flow),
# batch_size=args.batch_size//2, shuffle=False,
# num_workers=args.workers*2, pin_memory=pin_memory)
val_loader = torch.utils.data.DataLoader(BinaryDataSet(
args.feat_root,
args.feat_model,
val_prop_file,
subset_videos=val_videos,
exclude_empty=True,
body_seg=args.num_body_segments,
input_dim=args.d_model,
test_mode=True,
use_flow=args.use_flow,
verbose=False,
num_local=args.num_local,
only_flow=args.only_flow),
batch_size=1,
shuffle=False,
num_workers=10,
pin_memory=True)
ground_truth, cls_to_idx = grd_activity(
'data/activity_net.v1-3.min_save.json', subset='validation')
del cls_to_idx['background']
# optimizer = torch.optim.Adam(
# model.parameters(),
# args.lr, weight_decay=args.weight_decay)
optimizer = AdamW(model.parameters(),
args.lr,
weight_decay=args.weight_decay)
# optimizer = torch.optim.SGD(model.parameters(),
# args.lr,
# momentum=args.momentum,
# weight_decay=args.weight_decay, nesterov=False)
if args.resume is not None and len(args.resume) > 0:
model.load_state_dict(torch.load(args.resume)['state_dict'],
strict=False)
criterion_stage1 = CE_Criterion_multi(use_weight=True)
criterion_stage2 = Rank_Criterion(epsilon=0.02)
patience = 0
for epoch in range(args.start_epoch, args.epochs):
# adjust_learning_rate(optimizer, epoch, args.lr_steps)
# train for one epoch
if patience > 5:
break
train(train_loader, model, optimizer, criterion_stage1,
criterion_stage2, epoch, logger)
# evaluate on validation list
if (epoch + 1) % args.eval_freq == 0 or epoch == args.epochs - 1:
loss = validate(val_loader, model, ground_truth,
(epoch + 1) * len(train_loader), epoch)
# remember best prec@1 and save checkpoint
is_best = 1.0001 * loss < best_loss
if is_best:
patience = 0
else:
patience += 1
best_loss = min(loss, best_loss)
save_checkpoint(
{
'epoch': epoch + 1,
'arch': args.model,
'state_dict': model.state_dict(),
'best_loss': best_loss,
}, is_best, save_path)